Joint hyperbolic and Euclidean geometry contrastive graph neural networks
文献类型：期刊论文
| 作者 | Xu, Xiaoyu3,4 ; Pang, Guansong1,2; Wu, Di3,4; Shang, Mingsheng3,4
|
| 刊名 | INFORMATION SCIENCES
 |
| 出版日期 | 2022-09-01 |
| 卷号 | 609页码:799-815 |
| 关键词 | Graph neural networks Hyperbolic embedding Contrastive learning Graph representation learning |
| ISSN号 | 0020-0255 |
| DOI | 10.1016/j.ins.2022.07.060 |
| 通讯作者 | Pang, Guansong(gspang@smu.edu.sg) ; Shang, Mingsheng(msshang@cigit.ac.cn) |
| 英文摘要 | Graph Neural Networks (GNNs) have demonstrated state-of-the-art performance in a wide variety of analytical tasks. Current GNN approaches focus on learning representations in a Euclidean space, which are effective in capturing non-tree-like structural relations, but they fail to model complex relations in many real-world graphs, such as tree-like hierarchical graph structure. This paper instead proposes to learn representations in both Euclidean and hyperbolic spaces to model these two types of graph geometries. To this end, we introduce a novel approach - Joint hyperbolic and Euclidean geometry contrastive graph neural networks (JointGMC). JointGMC is enforced to learn multiple layer-wise optimal combinations of Euclidean and hyperbolic geometries to effectively encode diverse complex graph structures. Further, the performance of most GNNs relies heavily on the availability of large-scale manually labeled data. To mitigate this issue, JointGMC exploits proximitybased self-supervised information in different geometric spaces (i.e., Euclidean, hyperbolic, and Euclidean-hyperbolic interaction spaces) to regularize the (semi-) supervised graph learning. Extensive experimental results on eight real-world graph datasets show that JointGMC outperforms eight state-of-the-art GNN models in diverse graph mining tasks, including node classification, link prediction, and node clustering tasks, demonstrating JointGMC's superior graph representation ability. Code is available at https://github.com/chachatang/jointgmc. (c) 2022 Elsevier Inc. All rights reserved. |
| 资助项目 | National Natural Science Foundation of China[62072429] ; Chongqing Municipal Education Commission[HZ2021017] ; Chongqing Municipal Education Commission[HZ2021008] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000848168800012 |
| 出版者 | ELSEVIER SCIENCE INC |
| 源URL | [http://119.78.100.138/handle/2HOD01W0/16521]  |
| 专题 | 中国科学院重庆绿色智能技术研究院 |
| 通讯作者 | Pang, Guansong; Shang, Mingsheng |
| 作者单位 | 1.Singapore Management Univ, Sch Comp & Informat Syst, 80 Stamford Rd, Singapore 178902, Singapore 2.Singapore Management Univ, Sch Comp & Informat Syst, Singapore 178902, Singapore 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 4.Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing Key Lab Big Data & Intelligent Comp, Chongqing 400714, Peoples R China |
| 推荐引用方式 GB/T 7714 | Xu, Xiaoyu,Pang, Guansong,Wu, Di,et al. Joint hyperbolic and Euclidean geometry contrastive graph neural networks[J]. INFORMATION SCIENCES,2022,609:799-815. |
| APA | Xu, Xiaoyu,Pang, Guansong,Wu, Di,&Shang, Mingsheng.(2022).Joint hyperbolic and Euclidean geometry contrastive graph neural networks.INFORMATION SCIENCES,609,799-815. |
| MLA | Xu, Xiaoyu,et al."Joint hyperbolic and Euclidean geometry contrastive graph neural networks".INFORMATION SCIENCES 609(2022):799-815. |
入库方式： OAI收割
来源：重庆绿色智能技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。